In today′s aging society, the shortage of doctors may cause a delay of medical treatment. At the same time, the increasing expense of medical insurance has become a great burden to society. Therefore, we focus on the construction of a home doctor system intended to solve these problems. In this paper, we propose a construction approach of health checker and adviosr system for lifestyle-related diseases prevention. Firstly, the vague concept of medical knowledge is quantified by using fuzzy sets. Secondly, a method is developed to convert personal physiological time-series information into fuzzy membership functions. Furthermore, based on the Distance-Type Fuzzy Reasoning Method, reasoning algorithms of health checkup and health prediction are built up, which could be used to promote better lifestyles. Finally, the usability of proposed methods were discussed by the experiments of the health-check system.

View full abstract

The Self-organizing Map(SOM)is the most widely used artificial neural network algorithm in the unsupervised learning category. A clustering system is a major application of SOM. Normally, a SOM uses neurons of fixed size. However, it is hard to detemine the specific size of neurons that match the purpose of a clustering system, such as facial image clustering In this study, I propose a method that assesses the variation in the size of neurons according to the diversity of data. This method uses the Euclidean distance as an index to decide to whether insert a new neuron or eliminate a neuron. Test images of 3 and 26 patterns were inputted during the self-orgrnization process into the SOM which initially had 20 neurons. As a result, 7 and 69 neurons were obtained respectively. The proposed method created a clustering system that varied with the number of clusters. I applied the proposed method to classify facial images. I chose the infants′ facial images of 2 and 5 month old infants as test data, which had difference in complication of facial expressions. As a result, the number of clusters changed according to the variety of the infants′ facial egressions. Thus the proposed method is useful to make a clustering system for facial image analysis.

View full abstract

Social concern is increasing in preventing fall of aged. The improvement in aged people's walking ability is important for quality of life and fall prevention. In order to evaluate the improvement of the walking ability after medical footcare, walking balance, rotation range of ankle, knee elevation, and the moving distance of greater trochanter were investigated during the walk. And foot care worker values toe and toenail of malfunction. Subject testing was conducted on 10 elderly people (age range 73-96 years old) living in a special elderly nursing home. The coordinates of markers attached to the subject's greater trochanter, knee joint, ankle, turberosity of fifth metatarsal bone, and heel were measured using digital camcorder during the walk. The data was analyzed statistically. As a result of performing medical footcare for one year, rotation range of ankle, knee elevation, and walking balance during the walk improved, furthermore the moving of greater trochanter had stabilized. Because the medical footcare, which removes the interference from thickening of the nail, has strong correlation to the improvement of the rotation range of ankle, knee elevation, walking balance and moving of greater trochanter, it seems that it is effective to improve the walking ability of the aged. It is suggested that the medical footcare of the aged has possibility to exercise.

View full abstract

Magnetically compatible robots are required as haptic interfaces for enhancing neuroscience studies. The purpose of this paper is to develop an MRI compatible robot using ultrasonic motors, which is able to work within an MRI/ fMRI scanner and to acquire MR images continuously during hand motions. We propose a Manipulandum for hand motion. We measured the force distribution and joint angles of digits, and developed a new link model of a Manipulandum for hand motion. Our Manipulandum hand has one feature. It is the compact exoskeleton mechanism using ‘New link model’. ‘New link model’ was composed of 4-link mechanism, 6-link mechanism and 7-link mechanism, and one actuator of ‘enew link model’ is able to move all joints within the digits. However, these link mechanisms are limited in the movement. Finally, MRI compatibility of our manipulandum is verified experimentally.

View full abstract